Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    make something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pants
    0.46
    Tik
    0.45
     Tiktok
    0.45
     Panda
    0.44
     Jezus
    0.44
     tik
    0.42
    pants
    0.42
    ımda
    0.42
     personnalité
    0.42
     personalità
    0.42
    POSITIVE LOGITS
     &=
    0.40
     disorders
    0.39
     зали
    0.38
     prim
    0.37
     হত্যাকা
    0.35
    полни
    0.34
     হোমিওপ্যাথির
    0.34
    stoffen
    0.34
    UserProfile
    0.34
    &
    0.34
    Act Density 0.000%

    No Known Activations